© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9665
    Prev
    Next
    INDEX
    Explanations

    Negative situations/emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     troubled
    -1.25
     distressed
    -0.64
    trouble
    -0.50
    um
    -0.49
    as
    -0.46
     chậm
    -0.45
     just
    -0.43
    qu
    -0.43
     share
    -0.42
     then
    -0.42
    POSITIVE LOGITS
     дописавши
    0.88
    ResumeLayout
    0.79
     оригіналу
    0.78
    IntoConstraints
    0.77
    ]--;
    0.71
     ujednoznacz
    0.70
    CppCodeGen
    0.69
     AppColors
    0.66
    extAlignment
    0.65
    medriver
    0.65
    Activations Density 0.038%

    No Known Activations